Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically quotation marks and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    formatted string literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.51
     belts
    -0.46
     and
    -0.46
     tiers
    -0.45
     experience
    -0.44
     BaseActivity
    -0.44
    :✨
    -0.43
    ets
    -0.43
     APD
    -0.43
     AppBar
    -0.43
    POSITIVE LOGITS
    ?}",
    0.89
    !("{}",
    0.69
    {}",
    0.61
     %@",
    0.60
    (@"%@",
    0.59
    pecabe
    0.56
     <>",
    0.56
    %@",
    0.55
     {}",
    0.53
    genodigd
    0.53
    Act Density 0.005%

    No Known Activations